ShanghaiTech University
PulseAugur coverage of ShanghaiTech University — every cluster mentioning ShanghaiTech University across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New research tackles video anomaly detection with causal models and improved evaluation
Researchers are exploring new methods for video anomaly detection, focusing on improving efficiency and accuracy. One paper introduces a strictly causal streaming anomaly detector using a Mamba-style state-space model t…
-
New STEP framework improves human pose video anomaly detection
Researchers have developed a new framework called STEP (Score-Based Temporal Energy) for detecting anomalies in human pose videos. This method addresses a key challenge in existing approaches by using Principal Componen…
-
3D Gaussian Splatting advances towards embodied AI with efficiency and adaptability
Researchers are advancing 3D Gaussian Splatting (3DGS) beyond high-quality rendering to practical applications in embodied AI and robotics. Recent work presented at CVPR 2026 focuses on making 3DGS more efficient and ad…
-
New method enhances crowd instance segmentation using SAM and reinforced point selection
Researchers have developed a new method called Dense Point-to-Mask Optimization (DPMO) to improve instance segmentation in dense crowd scenarios. DPMO integrates the Segment Anything Model (SAM) with a Nearest Neighbor …
-
New AI Safety Method Introduces 'Ask First' Option
Researchers have developed a new method called Safety Sentry to improve the safety of AI agents. This approach moves beyond a simple binary safe/unsafe classification by introducing a third option: to ask for clarificat…
-
New framework SESAD improves video anomaly detection with structured reasoning
Researchers have developed a new framework called SESAD for weakly supervised video anomaly detection. This method tackles the challenge of accurately identifying anomalous events by treating anomaly detection as a stru…
-
Chinese startup Kuai Lin Optoelectronics secures funding for high-speed optical detector chips
Shanghai Kuai Lin Optoelectronics Technology Co., Ltd. (快粼光电) has secured tens of millions of yuan in angel funding to accelerate the mass production of its domestic ultra-high-speed photoelectric detection chips. The c…
-
AI surveillance benchmarks fail real-world tests, study finds
A new audit of AI surveillance systems reveals that benchmark performance metrics, specifically AUC scores, do not translate to real-world deployability. Researchers found that models trained on one dataset and scene pe…
-
VigilFormer framework enhances video anomaly detection with efficient attention
Researchers have developed VigilFormer, a novel framework for video anomaly detection that balances accuracy with real-time processing. The system utilizes a Deformable Spatio-Temporal Encoder to efficiently focus on re…
-
Computer vision shifts to 3D world modeling, moving beyond 2D images
Researchers are pushing computer vision beyond 2D image recognition towards a deeper understanding of the real world. This involves modeling 3D structures, cross-view consistency, temporal dynamics, and the observation …
-
New framework uses bounding-box trajectories for video anomaly detection
Researchers have developed TrajVAD, a new framework for video anomaly detection that utilizes bounding-box trajectories. This approach models normal kinematic patterns using normalizing flows, outperforming existing pos…
-
LLMs enhance video anomaly detection with reasoning and spatial grounding
Researchers have developed VANGUARD, a novel framework that integrates video anomaly detection with multimodal large language models. This system not only identifies anomalies but also provides interpretable chain-of-th…
-
Action Hints paper uses LLMs for skeleton-based video anomaly detection
Researchers have developed a new framework for zero-shot video anomaly detection (ZS-VAD) that leverages semantic typicality and context uniqueness from skeleton data. This approach aims to improve generalization to new…